© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57763
    Prev
    Next
    INDEX
    Explanations

    meat quality and processing

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology related to meat and muscle tissue in scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is highly sensitive to formal abstract nouns (especially those formed with suffixes like –ness or –tion) typical of academic or technical prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дзі
    -0.83
    huile
    -0.83
     Biomass
    -0.81
     棉
    -0.79
     daß
    -0.77
     执行
    -0.75
     biomass
    -0.75
    吭
    -0.75
     RIVER
    -0.74
    捎
    -0.74
    POSITIVE LOGITS
     tenderness
    1.01
     drip
    1.00
     muscle
    0.96
    Tender
    0.93
    drip
    0.92
     loin
    0.89
     Tender
    0.87
    Lean
    0.82
     instrumental
    0.81
     Lean
    0.81
    Activations Density 0.039%

    No Known Activations